Data Collection for Overlapping-Camera Calibration

Target-based

Calibration target

The Checkerboard is the calibration target. You can use the attached PDF. It has seven internal corners horizontally and nine internal corners vertically. https://drive.google.com/file/d/1mTR8HTpvROE1Pv0rmXEBVLSxs_yMDnvf/view?usp=sharing

Data Collection

Place the target in the overlapping field of view of the cameras and take an image from both cameras. Then, move the target all across the overlapping field of view of the cameras and take images from both cameras. For good extrinsic parameters, a minimum of 25 pairs of images is recommended.

Here is an example set of files used during this calibration process.

Calculating the intrinsic parameters for the left and right cameras is also recommended. Although the tool supports on-the-fly intrinsics calculations, we use the uploaded images for the intrinsic parameters, which tends to raise inaccuracies in the intrinsics calibration and overall Overlapping Calibration results.

Targetless

It is recommended that the scene have sufficient objects, textures, and unique patterns for feature detectors to identify and match. For example, the above calibration target example is not an ideal dataset for targetless as it has just a checkerboard in front of a plain white wall.

Here is an example set of files used during this calibration process.